In this section
@inproceedings{Zambelli:2016,
author = {Zambelli, M and Fischer, T and Petit, M and Chang, HJ and Cully, A and Demiris, Y},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
title = {Towards Anchoring Self-Learned Representations to Those of Other Agents},
url = {http://hdl.handle.net/10044/1/40970},
year = {2016}
}
TY - CPAPER
AB - In the future, robots will support humans in their every day activities. One particular challenge that robots will face is understanding and reasoning about the actions of other agents in order to cooperate effectively with humans. We propose to tackle this using a developmental framework, where the robot incrementally acquires knowledge, and in particular 1) self-learns a mapping between motor commands and sensory consequences, 2) rapidly acquires primitives and complex actions by verbal descriptions and instructions from a human partner, 3) discoverscorrespondences between the robots body and other articulated objects and agents, and 4) employs these correspondences to transfer the knowledge acquired from the robots point of view to the viewpoint of the other agent. We show that our approach requires very little a-priori knowledge to achieve imitation learning, to find correspondent body parts of humans, and allows taking the perspective of another agent. This represents a step towards the emergence of a mirror neuron like system based on self-learned representations.
AU - Zambelli,M
AU - Fischer,T
AU - Petit,M
AU - Chang,HJ
AU - Cully,A
AU - Demiris,Y
PB - Institute of Electrical and Electronics Engineers (IEEE)
PY - 2016///
TI - Towards Anchoring Self-Learned Representations to Those of Other Agents
UR - http://hdl.handle.net/10044/1/40970
ER -
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: